Model-based Radiostereometric Analysis Using Intensity-based 2D/3D Registration Pipeline: Feasibility Study

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F17%3APU126414" target="_blank" >RIV/00216305:26230/17:PU126414 - isvavai.cz</a>

Výsledek na webu

<a href="http://www.fit.vutbr.cz/research/pubs/all.php?id=11439" target="_blank" >http://www.fit.vutbr.cz/research/pubs/all.php?id=11439</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Model-based Radiostereometric Analysis Using Intensity-based 2D/3D Registration Pipeline: Feasibility Study

Popis výsledku v původním jazyce

Model-based radiostereometric analysis (MBRSA) methods exploit, in most cases, feature-based 2D/3D registration. In this paper we focus on a feasibilty of the intensity-based 2D/3D registration approach applied in MBRSA. To evaluate the feasibility, we created a data set containing stereo pairs of both synthetic and real radiographic images of a metallic radius bone implant. Evaluation, we performed and present, reveals sucient accuracy of the intensity-based registration pipeline and its robustness to image artifacts. The results obtained using synthetic radiographs show comparable accuracy with the feature-based non-overlapping area (NOA) approach. The registration process using real X-Ray images did not require preprocessing of the input radiographs neither was significantly affected by the presence of the metallic bone screws. This study presents an introductory part of an ongoing research.

Název v anglickém jazyce

Model-based Radiostereometric Analysis Using Intensity-based 2D/3D Registration Pipeline: Feasibility Study

Popis výsledku anglicky

Model-based radiostereometric analysis (MBRSA) methods exploit, in most cases, feature-based 2D/3D registration. In this paper we focus on a feasibilty of the intensity-based 2D/3D registration approach applied in MBRSA. To evaluate the feasibility, we created a data set containing stereo pairs of both synthetic and real radiographic images of a metallic radius bone implant. Evaluation, we performed and present, reveals sucient accuracy of the intensity-based registration pipeline and its robustness to image artifacts. The results obtained using synthetic radiographs show comparable accuracy with the feature-based non-overlapping area (NOA) approach. The registration process using real X-Ray images did not require preprocessing of the input radiographs neither was significantly affected by the presence of the metallic bone screws. This study presents an introductory part of an ongoing research.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2017

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Conference Materials and Posters of Spring Conference on Computer Graphics SCCG 2017

ISBN

—

ISSN

1335-5694

e-ISSN

—

Počet stran výsledku

3

Strana od-do

31-33

Název nakladatele

Brno University of Technology

Místo vydání

Mikulov

Místo konání akce

Mikulov

Datum konání akce

19. 4. 2017

Typ akce podle státní příslušnosti

EUR - Evropská akce

Kód UT WoS článku

—